<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2189">
  <Title>Using sentence connectors for evaluating MT output</Title>
  <Section position="7" start_page="1068" end_page="1068" type="concl">
    <SectionTitle>
6 Discussion
</SectionTitle>
    <Paragraph position="0"> The category means basically follow expectations.</Paragraph>
    <Paragraph position="1"> Those of C and 1) come ont a bit h)w, lint the combined mean for C+D suggests that this may be partly due to the size of the sample. The (:onjunct mean of B is very high; it is not clear why. It must be noted that the evMuators were totally untrained; in the context of the intended use of this method, requiring a certain level of training seems acceptable and this would surely bring resuits closer to tile goal of evaluator independence.</Paragraph>
    <Paragraph position="2"> llowever, we also observed several instances where the choice of a conjunct was dictated by the evah&gt; ator's prior knowledge (or lack of it) of the subject area; this is a discrepancy we cannot resolve.</Paragraph>
    <Paragraph position="3"> The cross-linguistic category mean for A+B is significantly lower than that of A+C and A+I).</Paragraph>
    <Paragraph position="4"> The conjunct mean is rather high: this is probably due to the unexplaine(\[ high conjunct mean for B. The conjunct means of A+C and A+I) seem to correlate with the number of unintelligible sentences in the machine-translated texts. Again the means of&amp;quot; A+C+I) are fairly enormous, indicating that size is still a factor.</Paragraph>
    <Paragraph position="5"> A rather unsettling result, however, was that the most-chosen sentence connector was identical across texts fur ahnost each of the sentence pairs.</Paragraph>
    <Paragraph position="6"> This suggests that redu(:ing evalnator dependence will lower all means, which would defeat the purpose of this research.</Paragraph>
    <Paragraph position="7"> In conclusion, we feel justified in hoping that, the goals of evalnatt)r-indei)endence, and languageimtependence are reachable through judicious tunlug of the. current systenL The project has also been successflll in that it has yielded a wealth of interesting data about sentence connections. 1t is (toubtflfl however that the approach will give a useful indication of translation quality.</Paragraph>
  </Section>
class="xml-element"></Paper>